QA Engineer - Agentic Gateway Testing

We are looking for a QA Engineer specialising in Agentic Gateway Testing to ensure the reliability, security, performance, and observability of agentic workflows and tool integrations. The role focuses on testing MCP-based interactions, multi-step agent workflows, authorization controls, performance characteristics, and end-to-end traceability across an enterprise agentic platform.About the ClientOur client is a large global enterprise operating across multiple markets, with a complex technology landscape and a strong focus on digital transformation and innovation. The organization is actively investing in modern cloud, data, and AI capabilities to enable scalable, secure, and highly automated solutions across its business.About the ProjectThe project is focused on building an enterprise-grade AI Agent Platform from the ground up. The platform will provide a standardized foundation for developing, deploying, orchestrating, securing, and observing AI agents across multiple teams and use cases.The initiative covers the full agent lifecycle and brings together agent orchestration, observability, security, governance, integrations, evaluation, and platform engineering. Engineers joining the project will have an opportunity to influence key architectural and technical decisions and contribute to a new platform rather than maintaining an existing solution.Skills:Agentic workflow testing — agent tool discovery, tool invocation, multi-step agent workflowsMCP protocol testing — tool list aggregation, tool call routing, streaming response handlingAgent authorization testing — unauthorized tool access attempts, policy enforcement validationAgent performance testing — tool discovery latency, concurrent agent sessions, agent-to-agent latencyPython test automation — pytest with async, mock MCP servers, agent workflow simulationAgentic observability validation — trace completeness, agent step logging, audit trail verificationExperience:4+ years QA engineering for AI/ML or agent systemsTested LLM agent workflows (tool calling, multi-step reasoning)Security testing for authorization and authenticationPerformance benchmarking for cloud servicesNice to have:MCP protocol testing experienceAgent framework testing (LangChain, LangGraph, Crew)AWS Bedrock Agents testingChaos engineering for agentic systemsAudit log validation (CloudTrail, OpenTelemetry traces)Responsibilities:Design and execute tests for agentic workflows, including tool discovery, tool invocation, and multi-step agent interactions.Validate MCP protocol behavior, including tool list aggregation, tool-call routing, and streaming responses.Test authorization and authentication controls, including unauthorized tool-access scenarios and policy-enforcement validation.Perform performance testing for agentic workloads, including tool-discovery latency, concurrent agent sessions, and agent-to-agent communication latency.Build and maintain automated tests in Python using pytest, including asynchronous testing, mock MCP servers, and agent workflow simulations.Validate agentic observability, including trace completeness, agent-step logging, and audit trails.Perform end-to-end testing across agent, gateway, and tool interaction flows.Identify reliability, security, and performance issues in complex agent workflows and support their resolution.